Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study

Abstract

Background Delays in the diagnosis of genetic syndromes are common, particularly in low and middle-income countries with limited access to genetic screening services. We, therefore, aimed to develop and evaluate a machine learning-based screening technology using facial photographs to evaluate a child's risk of presenting with a genetic syndrome for use at the point of care. MethodsIn this retrospective study, we developed a facial deep phenotyping technology based on deep neural networks and facial statistical shape models to screen children for genetic syndromes. We trained the machine learning models on facial photographs from children (aged <21 years) with a clinical or molecular diagnosis of a genetic syndrome and controls without a genetic syndrome matched for age, sex, and race or ethnicity. Images were obtained from three publicly available databases (the Atlas of Human Malformations in Diverse Populations of the National Human Genome Research Institute, Face2Gene, and the dataset available from Ferry and colleagues) and the archives of the Children's National Hospital (Washington, DC, USA), in addition to photographs taken on a standard smartphone at the Children's National Hospital. We designed a deep learning architecture structured into three neural networks, which performed image standardisation (Network A), facial morphology detection (Network B), and genetic syndrome risk estimation, accounting for phenotypic variations due to age, sex, and race or ethnicity (Network C). Data were divided randomly into 40 groups for cross validation, and the performance of the model was evaluated in terms of accuracy, sensitivity, and specificity in both the total population and stratified by race or ethnicity, age, and sex. Findings Our dataset included 2800 facial photographs of children (1318 [47%] female and 1482 [53%] male; 1576 [56%] White, 432 [15%] African, 430 [15%] Hispanic, and 362 [13%] Asian). 1400 children with 128 genetic conditions were included (the most prevalent being Williams-Beuren syndrome [19%], Cornelia de Lange syndrome [17%], Down syndrome [16%], 22q11.2 deletion [13%], and Noonan syndrome [12%] syndrome) in addition to 1400 photographs of matched controls. In the total population, our deep learning-based model had an accuracy of 88% (95% CI 87-89) for the detection of a genetic syndrome, with 90% sensitivity (95% CI 88-92) and 86% specificity (95% CI 84-88). Accuracy was greater in White (90%, 89-91) and Hispanic populations (91%, 88-94) than in African (84%, 81-87) and Asian populations (82%, 78-86). Accuracy was also similar in male (89%, 87-91) and female children (87%, 85-89), and similar in children younger than 2 years (86%, 84-88) and children aged 2 years or older (eg, 89% [87-91] for those aged 2 years to <5 years). Interpretation This genetic screening technology could support early risk stratification at the point of care in global populations, which has the potential accelerate diagnosis and reduce mortality and morbidity through preventive care.

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes

“…To provide examples of ways to bolster the standard diagnostic process as well as to build on the impressive findings of previous, related studies, ( Gurovich et al, 2019 ; Duong et al, 2021b ; Hsieh et al, 2021 ; Porras et al, 2021 ), we analyzed and provided a larger dataset of WS and 22q individuals (although these other studies contained a much larger total number of individuals having multiple other diseases). We also compared results for different ages of individuals.…”

“…There are additional potential approaches for depicting age progression, which we may explore in future studies ( Or-El et al, 2020 ). Of note, the previous work ( Gurovich et al, 2019 ; Porras et al, 2021 ) used different and/or additional age brackets, some of which may not involve sufficient numbers of images for robust analyses, at least in our datasets.…”

“…Neural networks are emerging as powerful tools in many areas of biomedical research and are starting to impact clinical care. In the field of genomics, these methods are applied in multiple ways, including generating differential diagnoses for patients with a possible genetic syndrome based on images, ( Gurovich et al, 2019 ; Hsieh et al, 2021 ; Porras et al, 2021 ), analysis of DNA sequencing data ( Luo et al, 2019 ) including phenotype-based annotation ( Clark et al, 2019 ) and variant classification ( Frazer et al, 2021 ), and prediction of the protein structure ( Baek et al, 2021 ; Jumper et al, 2021 ).…”

“…Such challenges can disproportionately impact older patients, as many clinical geneticists are initially trained in pediatric medicine and tend to focus on pediatric diagnosis ( Jenkins et al, 2021 ). Despite these issues, previous large-scale clinical genetic applications of neural networks studied populations affected by many different genetic conditions and yielded impressive results ( Gurovich et al, 2019 ; Porras et al, 2021 ). In the current study, we endeavored to build upon these existing works by collating our own age-annotated datasets.…”

Detection of Pitt–Hopkins Syndrome Based on Morphological Facial Features

“…Furthermore, the limited amount of data restricts the possibility of developing solutions based on deep learning approaches [15,[19][20][21] as these typically require very large amounts of training labelled data. In addition, besides the requirement of training data and significant computational resources, deep learning and in general Artificial Intelligence (AT) have sometimes been criticized for being a "black box" [22,23] which requires significant work to make them interpretable and/or explainable.…”